메뉴
Show your current knowledge state — what you know, what's decaying, study stats
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Connect a notification channel (Slack, Gmail, etc.) so Cognition can send you learning exercises throughout the day — even when your laptop is off.
Schedule learning exercises for the next 24 hours via Slack/Gmail. Runs at the end of every session so exercises arrive even when Claude Code is closed. The API decides WHEN and WHAT technique — you build the exercise and schedule delivery.
Send screen observations to the Cognition API as learning events. Transforms Screenpipe data into API event format.
Launch the Cognition GUI app. Opens the Electron window and connects Claude Code to it via WebSocket. Use this after /cognition:start or whenever you need the GUI.
Generate and deliver a learning exercise based on what the user is forgetting. Orchestrates different learning techniques.
Test if the user's confidence matches their actual knowledge. Use when calibration ECE is high or strategy is "overconfident".
| name | status |
| description | Show your current knowledge state — what you know, what's decaying, study stats |
TOKEN=$(cat ~/.cognition/token)
# Learner state (all concepts + recall probabilities)
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/learner-state?user_id=USER_ID"
# Recommendations (what needs attention)
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/recommendations?user_id=USER_ID&limit=10"
# Strategy signature (learner type)
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/strategy/signature?user_id=USER_ID"
# Calibration (confidence accuracy)
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/calibration/snapshot?user_id=USER_ID"
# Assessment report (mastery evidence)
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/assessment/report?user_id=USER_ID"
╔══════════════════════════════════════════════════╗
║ COGNITION STATUS ║
╠══════════════════════════════════════════════════╣
║ ║
║ Concepts tracked: 47 ║
║ Average recall: 74% ║
║ At risk (< 60%): 5 concepts ║
║ Strong (> 85%): 28 concepts ║
║ ║
║ LEARNING STYLE: stable_retriever ║
║ CALIBRATION: well-calibrated (ECE: 0.08) ║
║ ║
║ ── NEEDS REVIEW ────────────────────────────── ║
║ ⚠ React useEffect cleanup 43% 1.5d left ║
║ ⚠ SQL JOIN types 52% 3.0d left ║
║ △ Git rebase workflow 61% 5.0d left ║
║ △ Python decorators 64% 6.2d left ║
║ △ CSS Grid vs Flexbox 67% 7.1d left ║
║ ║
║ ── STRONGEST CONCEPTS ──────────────────────── ║
║ ✓ Python list comprehensions 92% ║
║ ✓ HTTP status codes 87% ║
║ ✓ JavaScript promises 86% ║
║ ║
║ ── TODAY'S STUDY ───────────────────────────── ║
║ Reviews completed: 8 ║
║ Accuracy: 87% ║
║ Concepts strengthened: 6 ║
║ ║
╚══════════════════════════════════════════════════╝
Fill in actual data from the API responses. Adjust the layout to fit the data.
If concepts are at risk, offer: "Want me to start a quick review? The most urgent concept is [X]."